Colloquium Series

Dr. Slobodan Vucetic, Professor and Chair, Computer and Information Sciences, Temple University

Thursday October 26, 2017 (11:00 - 12:00)

Deep Learning From Sequential Data

Abstract: In this talk we will discuss the state of the art approaches for descriptive and predictive analysis of sequential data, such as text and event logs. A critical challenge in the analysis of sequential data is data representation, which refers to converting the raw data into a form that is suitable for machine learning algorithms. Many machine learning algorithms, such as neural networks, require the input to be provided as a fixed-length vector and, for a long time, this has been considered a major obstacle for successful learning from sequential data. The recent progress in machine learning has resulted in several powerful ideas for better representation and learning from sequential data. Among these ideas, probably the most powerful are distributed representations and deep learning. We will describe the intuition behind these ideas and demonstrate their promise by showing our recent results on the analysis of micro-blogging data and medical records data.

Dr. Ani Nenkova, Associate Professor, University of Pennsylvania

Thursday October 5, 2017 (11:00 - 12:00)

Style Analysis for Practical Semantic Interpretation of Text

Abstract: Traditionally, natural language processing practitioners work under the assumption that the direct goal of text analysis is to ultimately derive a semantic interpretation of text. We explore alternatives to this tradition and instead focus on detecting style differences first, deferring or entirely foregoing semantic interpretation. This "style, then semantics if need be" approach to understanding reflects typical human behavior and may prove beneficial for many practical applications of language processing. Under style we hope to capture how content is conveyed rather than exactly what facts are being communicated or what truth values one ought to assign to the expressed statements.

Main challenges in style analysis are the lack of clear definition of the required stylistic dimensions and firm understanding of the granularity on which style should be analyzed. Here we present initial task-dependent style analysis in the context of automatic summarization. We present results on word-, sentence- and paragraph- level and show first results connecting style analysis on each of these levels and the performance of an automatic summarizer.

These results are part of a long-term research agenda aiming to establish style analysis as an integral area of computational linguistics research and to elucidates the specific mechanisms via which style modulates and enhances the semantic interpretation of text.

Saint Joseph's University, 5600 City Avenue, Philadelphia, PA 19131